> Magistral Small is an open-weights AI model from Mistral, released 10 Jun 2025. Index score 118 (GPT-4 = 100), rank 144 of 229 ranked models.

[Models](https://themodelindex.org/models/) /[Mistral](https://themodelindex.org/labs/mistral/)

# Magistral Small

Mistral

Released 10 Jun 2025

Open

Reasoning

Date verified

[Compare](https://themodelindex.org/compare/magistral-small-vs-o3-2025-04/) [Announcement](https://mistral.ai/news/magistral/)

118106–130

Index score

#144 of 229 models

2/ 8

Core tests taken

2 of 6 areas · plus 2 anchor tests

−29

Versus the frontier at release

best then: o3

Replaced by [Magistral Small 1.2](https://themodelindex.org/models/magistral-small-1-2/)

–

Price per million tokens

no public API price found

–

Context window

tokens it reads at once

## Where it sits · on the frontier

_Chart: Model Index score of every scored model since late 2022, with the best closed and best open model over time_

o1-mini reached this score 9 months earlier.

## Test results · by area · tick = best by any model

Show 2 anchor tests

Reasoning & knowledge

evidence

GPQA Diamond

56%

Humanity's Last Exam

no result

Maths

evidence

FrontierMath T1-3

no result

Coding

no evidence yet

SWE-bench Verified

no result

Terminal-Bench

no result

Agents

no evidence yet

APEX-Agents

no result

Novel problems

evidence

ARC-AGI-2

0%

Long tasks

no evidence yet

METR time horizon

no result

Independent results from the Epoch AI benchmarking hub, best reasoning setting. The core tests are shown here; anchor tests also inform the score and can be shown above.

## What others say · rank on each leaderboard

The Model Index

independent tests, our method

#144

of 219 · 118

Epoch Capabilities Index

overall capability from many benchmarks

#127

of 239 · 133.2

Further left is better. Leaderboards measure different things: LMArena is people voting blind between two answers, the others are test scores. Click any row for the source.

## Best at · top three among current models

Replaced by Magistral Small 1.2; it no longer leads any category among current models.

Where this model places in the top three of today's models, on category leaderboards and on our core tests.

## Where to use it · prices checked 1 Oct 2026

#### From the lab

Le Chat

app · subscription

↗

Mistral API

API

↗

Provider prices come from OpenRouter's live listing; going direct to a provider can differ. Subscriptions are the lab's own apps.

## Facts and sources

Released

10 Jun 2025

Announcement

[mistral.ai ↗](https://mistral.ai/news/magistral/)

Release entry

Magistral (Small/Medium)

Scored as

Magistral Small 1.0

Artificial Analysis index

–

Output speed

–

Hugging Face

not linked

## Mistral releases · around this one

Devstral

Open

21 MAY 2025

Magistral Medium

Closed

10 JUN 2025

Magistral Small

Open

10 JUN 2025

index 118

Mistral Large 3

Open

2 DEC 2025

Devstral 2

Open

9 DEC 2025

---
Source: https://themodelindex.org/models/magistral-small/ · The Model Index · data as of 2026-10-01